Using a Double-Well Oscillator to Train Binary Neural Network Layers

Abstract

Certain processors specifically designed for neural networks are defined with low-precision weights and activations. Low-precision weights and activations can considerably reduce the power required for computing a neural network. Although the neural network is still capable of generalizing the data to determine relevant features, the loss of precision in the values sometimes results in considerable loss of test accuracy. In this paper, we explore using a dynamical system which introduces transient chaos to the loss function that helps train binary network layers. Implementing theoretical stochastic rounding probabilities on the MNIST data set we improved the test error to state of the art for a binary network. We also show that adding a dynamical equation to the loss function of a network can effectively binarize a network.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 15, 2017
Accession Number
AD1059408

Entities

People

  • Aron Wing
  • Rose Rustowicz

Organizations

  • Rome Laboratory

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Accuracy
  • Air Force
  • Air Force Research Laboratories
  • Data Sets
  • Dynamics
  • Equations
  • Errors
  • Machine Learning
  • Military Research
  • Motivation
  • Neural Networks
  • Oscillators
  • Precision
  • Probability
  • Simulations
  • Switches
  • Training

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks